|
|
| 第43行： |
第43行： |
| | |Lantian Li | | |Lantian Li |
| | || | | || |
| − | * | + | * Enroll-test mismatch (test on large datasets) |
| | || | | || |
| − | * | + | * Enroll-test mismatch. |
| − | ||
| + | |
| − | *
| + | |
| | |- | | |- |
| | | | |
| People |
This Week |
Next Week |
Task Tracking (DeadLine)
|
| Dong Wang
|
- deepnorm2 paper refinement.
- More investigation on the optimum with NL, e.g., the global thresholding property
- Formulation for AV denosing and phone-aware DNF/NDA
- Continue the NB book.
|
- Complete the formulation of the AV denoising approach.
- Continue the NB book
|
|
| Yunqi Cai
|
- experiments on DNF2 and reconstructing paper structure
|
- experiments on New DNF2 paper
|
|
| Zhiyuan Tang
|
|
|
|
| Lantian Li
|
- Enroll-test mismatch (test on large datasets)
|
|
| Ying Shi
|
- Sub space flow plan A and plan B
- visulization and analysis of Sub space r code
|
- Continue on Sub-space flow
- Re-train a DAE model with state of the art result
|
|
| Haoran Sun
|
- Analyzed latent space of VAE and AE on TIMIT
|
- The same analysis on VAE with larger latent space dimension
- The same analysis on Glow
- Supervised approaches
|
|
| Yue Fan
|
|
|
|
| Jiawen Kang
|
- Prepare new Near-far data
- Collect experiments data
- Write multi-conditon paper
|
- Revise multi-conditon paper
- MAML experiments
|
|
| Ruiqi Liu
|
- Complete the experiment and write the paper.
|
|
|
| Haolin Chen
|
- Subspace Glow test
- Subspace Flow training and test
|
- Subspace Flow planA, B, cycle loss
|
|
